jev-routing

Go Jev harness for Claude Code, Codex, and Grok Build. No npx. Not an MCP server.

How it uses Jev

This repository is archived (2026-09-26). Based on our findings, we concluded that Jev-based tool selection and steering does not generically reduce AI agent token usage, and we ended development. It remains here to share the conclusions and the trial-and-error record. For the full history and data, see RESEARCH.md.

Getting started

Node is not required. Go 1.22+.

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README · the project website.

Keep exploring

Similar to jev-routing

Browse all
TypeSafe MCP project preview
Agent tooling
Bring typed Jev judgments to your coding assistant through a single MCP server.
nitro project preview
Agent tooling
Grok Build with TypeSafe Jev routing tool selection once per turn: 22 to 40% cheaper on the same tasks
jev-mcp (Songokou1983) project preview
Local MCP server exposing TypeSafe Jev (System One decision model) as native Claude Code / Codex tools
Jevbridge project preview
Browser & computer use
ACP and MCP adapter that bridges TypeSafe Jev with any LLM — computer use and typed decisions alongside Codex, Claude, Grok, and OpenCode.
WindowsJev project preview
Browser & computer use
Token-efficient Windows automation and durable research MCP server for Codex and Claude Code, powered by TypeSafe Jev.
hermes-jev-skills project preview
Browser & computer use
Jev-powered model routing, memory, compaction, skill selection, computer and browser use for Hermes agents (also Claude Code and Codex)
typesafe-jev-mcp project preview
Benchmarks & research
MCP server exposing TypeSafe's Jev model as a typed evaluate tool.
dohnuts project preview
Applications
Dohnuts builds small multimodal models for direct decisions. -> System One model
TypeSafe agent skills project preview
Official agent skill for Claude Code, Codex, and compatible agents: primitives, patterns, and how to structure evaluations.